Python中文分词工具使用详解

pip install jieba

import jieba
 
text = "厦门大学附属中山医院"
words = jieba.cut(text)
print( list(words) )

py test1.py

pip install snownlp

from snownlp import SnowNLP
 
text = "厦门大学附属中山医院"
s = SnowNLP(text)
words = s.words
print(words)

py test2.py

pip install thulac

import thulac
 
thu = thulac.thulac()
text = "厦门大学附属中山医院"
result = thu.cut(text)
print(result)

py test3.py

import jieba
from openpyxl import Workbook
 
# 创建一个新的工作簿
wb = Workbook()
# 选择默认的活动工作表
ws = wb.active
 
# 向工作表中写入表头
ws['A1'] = '分词'
 
# 读取文件
input_path = r"C:\Users\Administrator\Desktop\py\split words\demo\address.txt"
with open(input_path, 'r', encoding='utf-8') as input_file:
    for line in input_file:
        word = line.strip()
        print("---------"+word)
        words = jieba.cut( word )
        ll = list(words)
        for item in ll:
            print(item.strip())
            temp_list = []
            temp_list.append( item.strip() )
            ws.append(temp_list) 
                 
input_file.close()
# 保存工作簿
wb.save('output.xlsx')

py test.py